© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20242
    Prev
    Next
    INDEX
    Explanations

    phrases related to business operations, such as statements introducing new products, initiatives, or partnerships

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating direct quotations or speech in a context related to various industries or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kept
    -0.81
     somewhere
    -0.80
     interrog
    -0.80
    orno
    -0.77
     suspicion
    -0.76
     spor
    -0.76
     marginal
    -0.75
     fodder
    -0.75
     scept
    -0.74
    elsius
    -0.73
    POSITIVE LOGITS
     Executive
    1.07
     Director
    0.98
    CEO
    0.97
     Founder
    0.96
    ###
    0.95
    Executive
    0.95
     CEO
    0.94
     Principal
    0.93
     Marketing
    0.91
     Chairman
    0.89
    Activations Density 0.284%

    No Known Activations